AI models
RNMT+
Training compute
1.8×10¹⁹ FLOP
Parameters
378.9M
Published
Apr 26, 2018
RNMT+ is an AI model developed by Google AI (United States), first published in April 2018. It works in the language domain, on tasks such as translation.
Training it took an estimated 1.8×10¹⁹ FLOP of compute (estimation method: hardware,operation counting). The model has 378,900,000 parameters. Training ran on 32 NVIDIA P100 for about 120 hours.
Access: Unreleased. Its weights are not openly released. The reference paper has 504 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Google AI
- Country of organization
- United States
- Domain
- Language
- Task
- Translation
- Training compute
- 1.8×10¹⁹ FLOP
- Compute estimation method
- Hardware, Operation counting
- Parameters
- 378,900,000
- Training hardware
- NVIDIA P100
- Chips used
- 32
- Training time
- 120 h
- Chip-hours
- 3.8K
- Training power draw
- 16.6 kW
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 504
- Epoch confidence
- Likely
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models